{"id":"https://openalex.org/W7152966560","doi":"https://doi.org/10.48550/arxiv.2604.08545","title":"Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models","display_name":"Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152966560","doi":"https://doi.org/10.48550/arxiv.2604.08545"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.08545","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08545","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.08545","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133361710","display_name":"Shilin Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Shilin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111343895","display_name":"Jintao Tong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong, Jintao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133391846","display_name":"Hongwei Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Hongwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125244974","display_name":"Xiaojun Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Xiaojun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133393716","display_name":"Yangyang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yangyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133357480","display_name":"Kunyu Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Kunyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133344838","display_name":"Guannan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Guannan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133350135","display_name":"Ruixuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ruixuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133338325","display_name":"Yixiong Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Yixiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4032000005245209,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4032000005245209,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.0860000029206276,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.08160000294446945,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.48899999260902405},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4765999913215637},{"id":"https://openalex.org/keywords/cognitive-architecture","display_name":"Cognitive architecture","score":0.4738999903202057},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4300000071525574},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.32089999318122864},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.3109999895095825},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.30140000581741333},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3001999855041504}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7039999961853027},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C20854674","wikidata":"https://www.wikidata.org/wiki/Q4386060","display_name":"Cognitive architecture","level":3,"score":0.4738999903202057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43479999899864197},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4300000071525574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38260000944137573},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33970001339912415},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C150420422","wikidata":"https://www.wikidata.org/wiki/Q5141238","display_name":"Cognitive resource theory","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C21963081","wikidata":"https://www.wikidata.org/wiki/Q11337567","display_name":"Working memory","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C13200473","wikidata":"https://www.wikidata.org/wiki/Q2747831","display_name":"Reflexivity","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.08545","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08545","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.08545","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08545","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6091460585594177}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"advent":[1],"of":[2,117,218],"agentic":[3],"multimodal":[4],"models":[5],"has":[6],"empowered":[7],"systems":[8],"to":[9,26,41,46,80,148,196],"actively":[10],"interact":[11],"with":[12],"external":[13,34],"environments.":[14],"However,":[15],"current":[16],"agents":[17],"suffer":[18],"from":[19,55,143],"a":[20,84,108,137,144,149,191],"profound":[21],"meta-cognitive":[22],"deficit:":[23],"they":[24,37],"struggle":[25],"arbitrate":[27],"between":[28],"leveraging":[29],"internal":[30],"knowledge":[31],"and":[32,67,170],"querying":[33],"utilities.":[35],"Consequently,":[36],"frequently":[38],"fall":[39],"prey":[40],"blind":[42],"tool":[43,48,89,105,128,141,214],"invocation,":[44],"resorting":[45],"reflexive":[47],"execution":[49,176],"even":[50],"when":[51],"queries":[52],"are":[53],"resolvable":[54],"the":[56,115,118,194],"raw":[57],"visual":[58],"context.":[59],"This":[60,186],"pathological":[61],"behavior":[62],"precipitates":[63],"severe":[64],"latency":[65],"bottlenecks":[66],"injects":[68],"extraneous":[69],"noise":[70],"that":[71,87,139,166,174,208],"derails":[72],"sound":[73],"reasoning.":[74],"Existing":[75],"reinforcement":[76],"learning":[77],"protocols":[78],"attempt":[79],"mitigate":[81],"this":[82,92,132],"via":[83,182],"scalarized":[85],"reward":[86,120,155],"penalizes":[88],"usage.":[90],"Yet,":[91],"coupled":[93],"formulation":[94],"creates":[95],"an":[96,100,163,171],"irreconcilable":[97],"optimization":[98,161],"dilemma:":[99],"aggressive":[101],"penalty":[102,110],"suppresses":[103],"essential":[104],"use,":[106],"whereas":[107],"mild":[109],"is":[111],"entirely":[112],"subsumed":[113],"by":[114,216],"variance":[116],"accuracy":[119,164],"during":[121],"advantage":[122,184],"normalization,":[123],"rendering":[124],"it":[125],"impotent":[126],"against":[127],"overuse.":[129],"To":[130],"transcend":[131],"bottleneck,":[133],"we":[134],"propose":[135],"HDPO,":[136],"framework":[138],"reframes":[140],"efficiency":[142,172],"competing":[145],"scalar":[146],"objective":[147],"strictly":[150],"conditional":[151,183],"one.":[152],"By":[153],"eschewing":[154],"scalarization,":[156],"HDPO":[157],"maintains":[158],"two":[159],"orthogonal":[160],"channels:":[162],"channel":[165,173],"maximizes":[167],"task":[168,199],"correctness,":[169],"enforces":[175],"economy":[177],"exclusively":[178],"within":[179],"accurate":[180],"trajectories":[181],"estimation.":[185],"decoupled":[187],"architecture":[188],"naturally":[189],"induces":[190],"cognitive":[192],"curriculum-compelling":[193],"agent":[195],"first":[197],"master":[198],"resolution":[200],"before":[201],"refining":[202],"its":[203],"self-reliance.":[204],"Extensive":[205],"evaluations":[206],"demonstrate":[207],"our":[209],"resulting":[210],"model,":[211],"Metis,":[212],"reduces":[213],"invocations":[215],"orders":[217],"magnitude":[219],"while":[220],"simultaneously":[221],"elevating":[222],"reasoning":[223],"accuracy.":[224]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-11T00:00:00"}